Visual Object Tracking using Neural Networks for Embedded Systems
Kostiantyn Verhun, Mykola Dyvak · 2025
This paper considers a task of visual object tracking with application in embedded systems. Specifically, Raspberry Pi is considered as target hardware platform. The main challenge in this problem setting is to balance between algorithm result quality and its runtime efficiency. To select the method, the main object tracking approaches were analyzed and compared. Based on this, Nanotrack method was picked for deeper analysis and experiments. Method results accuracy was analyzed by already available benchmark scores and by running test on handpicked cases from LaSOT dataset highlighting different challenges for object tracking methods such as occlusion, scale variability, etc. The runtime performance was measured using target hardware. Based on the obtained results it was concluded that selected method is suitable to perform real time object tracking in the target setting, and further development will be based on this method.